Spaces:
Running on Zero
Running on Zero
Add tiny GGUF CPU control test
Browse files
app.py
CHANGED
|
@@ -195,6 +195,7 @@ except ImportError:
|
|
| 195 |
# ---------------------------------------------------------------------------
|
| 196 |
|
| 197 |
_BENCH_MODELS = [
|
|
|
|
| 198 |
{"name": "Gemma 4 E4B", "repo": "unsloth/gemma-4-E4B-it-GGUF", "file": "gemma-4-E4B-it-Q4_K_M.gguf", "size_gb": 2.5},
|
| 199 |
{"name": "Qwen3 8B", "repo": "Qwen/Qwen3-8B-GGUF", "file": "Qwen3-8B-Q4_K_M.gguf", "size_gb": 5.0},
|
| 200 |
{"name": "Qwen3.8 27B", "repo": "unsloth/Qwen3.8-27B-GGUF", "file": "Qwen3.8-27B-Q4_0.gguf", "size_gb": 16.0},
|
|
@@ -304,6 +305,7 @@ def _run_cpu_smoke(model_filter):
|
|
| 304 |
"engine": "llama-cli",
|
| 305 |
"gpu_layers": 0,
|
| 306 |
"threads": _parse_cpu_count() or 8,
|
|
|
|
| 307 |
"phases": {},
|
| 308 |
}
|
| 309 |
|
|
|
|
| 195 |
# ---------------------------------------------------------------------------
|
| 196 |
|
| 197 |
_BENCH_MODELS = [
|
| 198 |
+
{"name": "TinyLlama 1.1B (control)", "repo": "TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF", "file": "tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf", "size_gb": 0.7},
|
| 199 |
{"name": "Gemma 4 E4B", "repo": "unsloth/gemma-4-E4B-it-GGUF", "file": "gemma-4-E4B-it-Q4_K_M.gguf", "size_gb": 2.5},
|
| 200 |
{"name": "Qwen3 8B", "repo": "Qwen/Qwen3-8B-GGUF", "file": "Qwen3-8B-Q4_K_M.gguf", "size_gb": 5.0},
|
| 201 |
{"name": "Qwen3.8 27B", "repo": "unsloth/Qwen3.8-27B-GGUF", "file": "Qwen3.8-27B-Q4_0.gguf", "size_gb": 16.0},
|
|
|
|
| 305 |
"engine": "llama-cli",
|
| 306 |
"gpu_layers": 0,
|
| 307 |
"threads": _parse_cpu_count() or 8,
|
| 308 |
+
"no_mmap": True,
|
| 309 |
"phases": {},
|
| 310 |
}
|
| 311 |
|